Background:　Lung　cancer　has　the　highest　morbidity　and　mortality　worldwide,　and　lung　adenocarcinoma　(LADC)　is　the　most　common　pathological　subtype.　Accumulating　evidence　suggests　the　tumor　microenvironment　(TME)　is　correlated　with　the　tumor　progress　and　the　patient＇s　outcome.　As　the　major　components　of　TME,　the　tumor-infiltrated　immune　cells　and　stromal　cells　have　attracted　more　and　more　attention.　In　this　study,　differentially　expressed　immune　and　stromal　signature　genes　were　used　to　construct　a　TME-related　prognostic　model　for　predicting　the　outcomes　of　LADC　patients.　Methods:　The　expression　profiles　of　LADC　samples　with　clinical　information　were　obtained　from　The　Cancer　Genome　Atlas　(TCGA)　and　Gene　Expression　Omnibus　(GEO).　The　differentially　expressed　genes　(DEGs)　related　to　the　TME　of　LADC　were　identified　using　TCGA　dataset　by　Wilcoxon　rank　sum　test.　The　prognostic　effects　of　TME-related　DEGs　were　analyzed　using　univariate　Cox　regression.　Then,　the　least　absolute　shrinkage　and　selection　operator　(LASSO)　regression　was　performed　to　reduce　the　overfit　and　the　number　of　genes　for　further　analysis.　Next,　the　prognostic　model　was　constructed　by　step　multivariate　Cox　regression　and　risk　score　of　each　sample　was　calculated.　Then,　survival　and　Receiver　Operating　Characteristic　(ROC)　analyses　were　conducted　to　validate　the　model　using　TCGA　and　GEO　datasets,　respectively.　The　Kyoto　Encyclopedia　of　Genes　and　Genomes　analysis　of　gene　signature　was　performed　using　Gene　Set　Enrichment　Analysis　(GSEA).　Finally,　the　overall　immune　status,　tumor　purity　and　the　expression　profiles　of　HLA　genes　of　high-　and　low-risk　samples　was　further　analyzed　to　reveal　the　potential　mechanisms　of　prognostic　effects　of　the　model.　Results:　A　total　of　93　TME-related　DEGs　were　identified,　of　which　23　DEGs　were　up-regulated　and　70　DEGs　were　down-regulated.　The　univariate　cox　analysis　indicated　that　23　DEGs　has　the　prognostic　effects,　the　hazard　ratio　ranged　from　0.65　to　1.25　(p　＜　0.05).　Then,　seven　genes　were　screened　out　from　the　23　DEGs　by　LASSO　regression　method　and　were　further　analyzed　by　step　multivariate　Cox　regression.　Finally,　a　three-gene　(ADAM12,　Bruton　Tyrosine　Kinase　(BTK),　ERG)　signature　was　constructed,　and　ADAM12,　BTK　can　be　used　as　independent　prognostic　factors.　The　three-gene　signature　well　stratified　the　LADC　patients　in　both　training　(TCGA)　and　testing　(GEO)　datasets　as　high-risk　and　low-risk　groups,　the　3-year　area　under　curve　(AUC)　of　ROC　curves　of　three　GEO　sets　were　0.718　(GSE3141),　0.646　(GSE30219)　and　0.643　(GSE50081).　The　GSEA　analysis　indicated　that　highly　expressed　ADAM12,　BTK,　ERG　mainly　correlated　with　the　activation　of　pathways　involving　in　focal　adhesion,　immune　regulation.　The　immune　analysis　indicated　that　the　low-risk　group　has　more　immune　activities　and　higher　expression　of　HLA　genes　than　that　of　the　high-risk　group.　In　sum,　we　identified　and　constructed　a　three　TME-related　DEGs　signature,　which　could　be　used　to　predict　the　prognosis　of　LADC　patients.